SpectrumRBFKernel.h

Go to the documentation of this file.

/*
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 3 of the License, or
 * (at your option) any later version.
 *
 * Written (W) 1999-2009 Soeren Sonnenburg
 * Written (W) 1999-2008 Gunnar Raetsch
 * Copyright (C) 1999-2009 Fraunhofer Institute FIRST and Max-Planck-Society
 */

#ifndef _SPECTRUMRBFKERNEL_H___
#define _SPECTRUMRBFKERNEL_H___

#include <shogun/lib/common.h>
#include <shogun/lib/Trie.h>
#include <shogun/kernel/string/StringKernel.h>
#include <shogun/features/StringFeatures.h>


#include <shogun/lib/DynamicArray.h>

#include <vector> // profile
#include <string> // profile

namespace shogun
{

class CSpectrumRBFKernel: public CStringKernel<char>
{
    public:
        CSpectrumRBFKernel();

        CSpectrumRBFKernel(int32_t size, float64_t* AA_matrix, int32_t degree, float64_t width);

        CSpectrumRBFKernel(
            CStringFeatures<char>* l, CStringFeatures<char>* r, int32_t size, float64_t* AA_matrix, int32_t degree, float64_t width);

        virtual ~CSpectrumRBFKernel();

        virtual bool init(CFeatures* l, CFeatures* r);

        virtual void cleanup();

        int32_t get_degree() const
        {
            return degree;
        }

        virtual EKernelType get_kernel_type() { return K_SPECTRUMRBF; }

        virtual const char* get_name() const { return "SpectrumRBFKernel"; }

        inline bool set_degree(int32_t deg) { degree=deg; return true; }

        inline int32_t get_degree() { return degree; }

        bool set_AA_matrix(float64_t* AA_matrix_);

    protected:

        float64_t AA_helper(const char* path, const int degree, const char* joint_seq, unsigned int index);

        void read_profiles_and_sequences();

        float64_t compute(int32_t idx_a, int32_t idx_b);

        virtual void remove_lhs();
        virtual void register_param();
        void register_alphabet();


    protected:
        CAlphabet* alphabet;
        int32_t degree;
        int32_t max_mismatch;
        float64_t* AA_matrix ;
        int32_t AA_matrix_length;
        float64_t width;

        //int32_t* aa_to_index; // profile

        //double background[20]; // profile
        std::vector< std::vector<float64_t> > profiles; //profile
        std::vector<std::string> sequence_labels; // profile
        SGString<char>* sequences; // profile
        CStringFeatures<char>* string_features;
        int32_t nof_sequences;
        int32_t max_sequence_length;

        bool initialized;
        CDynamicArray<float64_t> kernel_matrix; // 2d
        int32_t target_letter_0;

    private:
        void init();
};

}



#endif /* _SPECTRUMMISMATCHRBFKERNEL_H__ */